Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExplaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks
شرح تنبؤات الشبكة العصبية في أزواج الجملة عبر أقنعة تعلم مجموعة الكلمات
472
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
شرح نماذج الشبكة العصبية مهمة لزيادة جدورث بالثقة في تطبيقات العالم الحقيقي. توليد معظم الأساليب الموجودة تفسيرات ما بعد الهخص لنماذج الشبكة العصبية من خلال تحديد وسمات الميزات الفردية أو الكشف عن التفاعلات بين الميزات المجاورة. ومع ذلك، بالنسبة للنماذج التي تحتوي على أزواج نصية كدخلات (على سبيل المثال، التعريف بإعادة صياغة التعريف)، فإن الأساليب الموجودة ليست كافية لالتقاط تفاعلات الميزات بين نصين وتمديدها البسيط لحساب جميع تفاعلات Word-Beach بين نصفي غير فعال. في هذا العمل، نقترح طريقة Group Mask (GMASK) لتكتشف ضمنيا علاقات الكلمات من خلال تجميع الكلمات المرتبطة من زوج إدخال الإدخال معا وقياس مساهمتها في مهام NLP المقابلة ككل. يتم تقييم الطريقة المقترحة مع اثنين من بنية نموذجية مختلفة (نموذج الاهتمام للتحلل) عبر أربع مجموعات بيانات، بما في ذلك الاستدلال اللغوي الطبيعي وإعادة صياغة مهام التعريف. تظهر التجارب فعالية Gmask في توفير تفسيرات مخلصة لهذه النماذج.
Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or detecting interactions between adjacent features. However, for models with text pairs as inputs (e.g., paraphrase identification), existing methods are not sufficient to capture feature interactions between two texts and their simple extension of computing all word-pair interactions between two texts is computationally inefficient. In this work, we propose the Group Mask (GMASK) method to implicitly detect word correlations by grouping correlated words from the input text pair together and measure their contribution to the corresponding NLP tasks as a whole. The proposed method is evaluated with two different model architectures (decomposable attention model and BERT) across four datasets, including natural language inference and paraphrase identification tasks. Experiments show the effectiveness of GMASK in providing faithful explanations to these models.
References used
https://aclanthology.org/
rate research
Read More
We offer an approach to explain Decision Tree (DT) predictions by addressing potential conflicts between aspects of these predictions and plausible expectations licensed by background information. We define four types of conflicts, operationalize the
ir identification, and specify explanatory schemas that address them. Our human evaluation focused on the effect of explanations on users' understanding of a DT's reasoning and their willingness to act on its predictions. The results show that (1) explanations that address potential conflicts are considered at least as good as baseline explanations that just follow a DT path; and (2) the conflict-based explanations are deemed especially valuable when users' expectations disagree with the DT's predictions.
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investi
gated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
Modern approaches to Constituency Parsing are mono-lingual supervised approaches which require large amount of labelled data to be trained on, thus limiting their utility to only a handful of high-resource languages. To address this issue of data-spa
rsity for low-resource languages we propose Universal Recurrent Neural Network Grammars (UniRNNG) which is a multi-lingual variant of the popular Recurrent Neural Network Grammars (RNNG) model for constituency parsing. UniRNNG involves Cross-lingual Transfer Learning for Constituency Parsing task. The architecture of UniRNNG is inspired by Principle and Parameter theory proposed by Noam Chomsky. UniRNNG utilises the linguistic typology knowledge available as feature-values within WALS database, to generalize over multiple languages. Once trained on sufficiently diverse polyglot corpus UniRNNG can be applied to any natural language thus making it Language-agnostic constituency parser. Experiments reveal that our proposed UniRNNG outperform state-of-the-art baseline approaches for most of the target languages, for which these are tested.
This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment errors by rel
ying mainly on uninformative tokens from the source sequence. However, we observe that NMT models assign attention to these tokens to regulate the contribution in the prediction of the two contexts, the source and the prefix of the target sequence. We provide evidence about the influence of wrong alignments on the model behavior, demonstrating that the encoder-decoder attention mechanism is well suited as an interpretability method for NMT. Finally, based on our analysis, we propose methods that largely reduce the word alignment error rate compared to standard induced alignments from attention weights.
Translation divergences are varied and widespread, challenging approaches that rely on parallel text. To annotate translation divergences, we propose a schema grounded in the Abstract Meaning Representation (AMR), a sentence-level semantic framework
instantiated for a number of languages. By comparing parallel AMR graphs, we can identify specific points of divergence. Each divergence is labeled with both a type and a cause. We release a small corpus of annotated English-Spanish data, and analyze the annotations in our corpus.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
